AI News

Second Thoughts: Exploring and Planning through Comparative Imagination in World Models (arxiv.org)

The Reflexivity Threshold: A Phase Transition for Multi-Agent Performative Prediction (arxiv.org)

Fast Bayesian Optimization Through Linear Models (arxiv.org)

A Transfer Learning-Driven Methodology for Efficient and Sustainable Indoor Localization Using VLC (arxiv.org)

Local and Global Recursive Ridge Regression for Online Residual Correction of Frozen Multivariate Forecasters under Label Delay (arxiv.org)

Improved Training of Strong Stochastic Flow Maps (arxiv.org)

Reliability-Aware Probabilistic Fusion for Multimodal Learning with Incomplete Evidence (arxiv.org)

Preventing Model Extraction in Contextual Linear Optimization (arxiv.org)

Cross-Area Transfer Learning for VLC-based Indoor Localization with a Transfer Efficiency Score (arxiv.org)

Probabilistic Machine Learning for Short-Term Atmospheric Seeing Forecasting (arxiv.org)

SPARE: Sparsity Allocation via Routing Entropy for Efficient MoEs (arxiv.org)

Leveraging Time-Series Foundation Models for Financial Crime Detection (arxiv.org)

Privacy in Context Is Being Overlooked in the Age of General-Purpose LLMs (arxiv.org)

Characterizing Oblivious Common-Reward Multi-Player Bandits: Universal Stationarity, Coordination Traps, and Certified Global Rates (arxiv.org)

DriveMLP: When Training Strategy Outperforms Model Complexity in Autonomous Driving (arxiv.org)

Structure-Aware Message Passing on Petri Nets through Directed Walks and Incidence Diffusion (arxiv.org)

Monitorability Is Trainable: Post-Training for Chain-of-Thought Monitorability (arxiv.org)

A Sharp Dynamic Haussler Lemma (arxiv.org)

Your Benchmark Is an Empirical Measure Over Difficulty (arxiv.org)

FrontierCS 2: A Benchmark for Computer Science R&D (arxiv.org)

CORD: Conflict-Aware Optimization for Joint RL and Distillation in Agents (arxiv.org)

SCDM: Scalable Causal Discovery in Nonlinear Temporal Systems with Meta-Learning (arxiv.org)

No Frames, Just Frequencies: Bandwidth-Efficient Deployment-Time Adaptation for Smart Glasses (arxiv.org)

Watch Your Step: Anticipated Perception for Humanoid Locomotion (arxiv.org)

Space weather dependence of decameter-scale ionospheric irregularities spatial distribution (arxiv.org)

Recursive Code Evolution for Task-Oriented Semantic Communications (arxiv.org)

Lineage-Aware Search Control for LLM-Based Evolutionary Factor Mining (arxiv.org)

TraceForge: Distilling with Your Own Thinking (arxiv.org)

Supermodular Rank: Set Function Decomposition and Optimization (arxiv.org)

Rethinking Post-hoc Debiasing of Large Pretrained Models (arxiv.org)

Where Do LLMs Learn to Recommend AI? (arxiv.org)

Real PMIDs, Wrong Papers: Harness Design for Biomedical Claim-Verification Agents (arxiv.org)

NeuroCodec: EEG-Guided Latent-Domain Generative Model for High-Fidelity Target Speaker Extraction (arxiv.org)

RangeNav: Task-Aligned LiDAR Range-Image Pretraining for Robot Navigation (arxiv.org)

Tractable Inference with Kolmogorov-Arnold Networks (arxiv.org)

A Generalisation Signal Need Not Be a Model-Selection Signal (arxiv.org)

Physics is the Best Teacher: Consistency Learning for Time-Invariant Operators of Chaotic Dynamics (arxiv.org)

TrustmeWatcher: An Application for Workplace Micro-Sensing and Explainable Well-Being Feedback (arxiv.org)

Compression Through Time: An Interplay of Separability, Stationarity and Capacity (arxiv.org)

An important Bottleneck in LLM Optimizers: Principle-Level Local Optima (arxiv.org)

Self-organizing reinforcement learning: a learner-free swarm approaches the explore-exploit optimum (arxiv.org)

Copying Under Repetition: From Prefix Matching to Position Hashing (arxiv.org)

Bilateral Sharpness-Aware Minimization for Flatter Minima (arxiv.org)

AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems (arxiv.org)

Learning to Interfere in Non-Orthogonal Multiple-Access Joint Source-Channel Coding (arxiv.org)

Synthesis and Verification of Register Automata over Data Sequences (Technical Report) (arxiv.org)

RubRIX: Rubric-Driven Risk Mitigation in Caregiver-AI Interactions (arxiv.org)

ExGrad: Beyond Suppression - Explicit Clean-Gradient Subtraction in Adversarial Training (arxiv.org)

Loopholing All the Way: Language Modeling with pure Self-Conditioning (arxiv.org)

From Classifier Heads to Encoder Prototypes: Personalized Federated Learning with Head-Derived Clustering (arxiv.org)